© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39805
    Prev
    Next
    INDEX
    Explanations

    closing and opening delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leist
    -0.07
     vân
    -0.07
    aines
    -0.07
    .vars
    -0.06
    nonnull
    -0.06
    èĪį
    -0.06
    æ¯Ľ
    -0.06
    гоÑĤов
    -0.06
    éĢĤåºĶ
    -0.06
    .getSelected
    -0.06
    POSITIVE LOGITS
    åµĮå¥Ĺ
    0.10
    éħį对
    0.10
     pairing
    0.09
     opening
    0.09
     Opening
    0.08
    Opening
    0.08
     parentheses
    0.08
    ç»ĵ对
    0.08
    æĭ¬
    0.08
     parenthesis
    0.08
    Activations Density 0.012%

    No Known Activations